An experiment in automatic indexing using the HASSET thesaurus (original) (raw)

AI-generated Abstract

The paper explores the application of the KEA (Keyword Extraction Algorithm) tool for automatic indexing of a collection of documents from the UK Data Archive using the HASSET thesaurus. The study compares KEA-generated keywords against manually assigned 'gold standard' keywords, evaluating its effectiveness through metrics such as precision, recall, and F1-score. Results indicate that while KEA can aid indexers, it is most effective as a suggestive tool when complemented by human oversight, with recommendations for further investigation and integration into metadata processes.

Sign up for access to the world's latest research.

checkGet notified about relevant papers

checkSave papers to use in your research

checkJoin the discussion with peers

checkTrack your impact